All Issue

2025 Vol.60, Issue 5 Preview Page

Research Article

Predicting Fear of Crime and Evaluating CPTED-based Crime Safety Design Using Street View Images and Deep Learning

거리영상과 딥러닝을 활용한 범죄 불안감 예측 및 CPTED 기반 범죄 안전 설계 평가

Somang Kima
,
Youngok Kangb*
김 소망a
,
강 영옥b*
aMA Student, Department of Social Studies(Geography), Ewha Womans University
bProfessor, Department of Social Studies(Geography), Ewha Womans University
a이화여자대학교 일반대학원 사회과교육학과 지리학전공 석사과정
b이화여자대학교 사회과교육과 교수
*Corresponding Author
31 October 2025. pp. 576-592
PDF XML Citation
Abstract

This study proposes a methodology for quantitatively evaluating fear of crime and crime safety based on Crime Prevention Through Environmental Design (CPTED) using street view imagery. Taking Yeongdeungpo-gu, Seoul as a case study, approximately 87,000 street view images were collected, with 30% used to construct a training dataset for deep learning. Fear of crime scores were predicted using the RSS-Swin model, which incorporates a Siamese Network, RankNet architecture, and a Swin Transformer backbone. Simultaneously, 15 quantitative CPTED indicators were developed, and semantic segmentation of street images and GIS data were used to compute crime safety design scores. Results indicated that older residential and industrial areas exhibited both higher fear of crime and lower CPTED-based design quality, while high-rise residential and commercial districts showed greater perceived and physical safety. A bivariate map integrating both metrics revealed four spatial patterns, providing policy-relevant insights. This study contributes an integrated framework combining perceptual and physical safety assessments, supporting more effective urban environment improvements and crime prevention strategies.

Keywords
Street View Images(SVI)
Crime Prevention Through Environmental Design (CPTED)
Fear of Crime
RSS-Swin model
Semantic Segmentation

본 연구는 거리 영상을 활용하여 도시의 범죄 불안감과 CPTED(crime prevention through environmental design) 기반 범죄 안전 설계를 정량적으로 평가하는 방법론을 제시하였다. 서울시 영등포구를 사례로, 약 87,000장의 거리 영상을 수집하고 이 중 30%를 기반으로 딥러닝 훈련 데이터셋을 구축하였다. 범죄 불안감 점수는 Siamese Network와 RankNet 구조, Swin Transformer 백본을 활용한 RSS-Swin 모델을 통해 예측하였고, 예측된 결과를 지도화하였다. 동시에, CPTED 이론에 근거한 15개의 정량적 평가 지표를 개발하고, 거리 영상의 시맨틱 세그멘테이션과 GIS 데이터를 활용하여 범죄 안전 설계 점수를 산출하였다. 분석 결과, 노후 주거지 및 공업지대는 범죄 불안감이 높고, 범죄예방 설계 수준도 취약한 것으로 나타났으며, 고층 아파트 밀집 지역과 업무지구는 전반적으로 안전성이 높았다. 특히, 범죄 불안감과 범죄 안전 설계 결과를 이변량 지도로 통합 분석함으로써 네 가지 유형의 공간적 패턴을 도출하였고, 그에 따른 정책적 시사점을 제안하였다. 본 연구는 인지적 감성과 물리적 설계의 통합적 평가틀을 제시함으로써 도시환경 개선과 범죄예방 전략 수립에 기여할 수 있는 기반을 마련하였다는 점에 의의가 있다.

키워드
거리 영상
범죄예방환경설계
범죄불안감
RSS-Swin 모델
시멘틱 세그먼테이션
References
1

강부성･이유미･박현호･성기호･임동현, 2012, “범죄로부터 안전한 골목길 평가에 관한 연구,” 한국셉테드학회지, 3(1), 5-36.

2

강승영･안수미･손광호, 2014, “안전한 주거환경 조선을 위한 범죄예방 환경디자인 제안,” 한국실내디자인학회 논문집, 23(6), 150-159.

10.14774/JKIID.2014.23.6.150
3

강영옥, 2023, “GeoAI 활용 분야와 연구 동향,” 대한지리학회지, 58(4), 395-418.

10.22776/kgs.2023.58.4.395
4

경찰청, 2013, 환경설계를 통한 범죄예방(CPTED) 방안, 서울.

5

국토교통부, 2013, 건축물의 범죄예방설계 가이드라인, 세종.

6

김소망･최재연･강영옥, 2024, “거리영상과 딥러닝을 활용한 가로수준의 범죄불안감 측정 및 시각화,” 한국지도학회지, 24(1), 71-84.

10.16879/jkca.2024.24.1.071
7

김지연･강영옥, 2022, “거리영상 기반 보행환경의 정성적 평가 예측을 위한 딥러닝 모델 개발,” 대한공간정보학회지, 30(2), 45-56.

10.7319/kogsis.2022.30.2.045
8

박승훈, 2014, “주택유형이 범죄에 미치는 영향 분석 - 서울시 25개 자치구를 중심으로 -,” 한국주거학회논문집, 25(3), 85-92.

10.6107/JKHA.2014.25.3.085
9

박종훈･임형백･이성우, 2017, “패널모형을 적용한 5대 범죄발생의 결정요인에 관한 연구,” 한국지역개발학회지, 29(2), 133-160.

10

박지영･강영옥･김지연, 2022, “거리 영상과 시멘틱 세그먼테이션을 활용한 보행환경 평가 지표 개발,” 한국지도학회지, 22(1), 53-68.

10.16879/jkca.2022.22.1.053
11

변기동･하미경, 2019, “AHP분석을 통한 도시옥외공공공간의 범죄안전 평가지표 분석,” 대한건축학회 논문집 - 계획계, 35(5), 11-20.

12

서울특별시, 2013, 범죄예방환경설계 (CPTED) 가이드라인, 서울.

13

서울특별시, 2021, 5대 범죄 발생현황 통계, 서울.

14

유광흠･진현영, 2012, 건축도시공간연구소 범죄예방을 위한 환경설계 지침 연구. 국립중앙도서관, 서울.

15

유기현･이동기･이창우･남광우, 2022, “크라우드 소싱 기반 딥러닝 선호 학습을 위한 쌍체 비교 셋 생성,” 한국산업정보학회논문지, 27(5), 1-11.

16

윤소진･이승재･강석진, 2012, “CPTED 관점에서 안전한 대학교캠퍼스를 위한 적용요소 연구,” 대한건축학회 논문집 - 계획계, 28(3), 119-126.

17

최재연, 김소망, 강영옥, 2024a, “어디가 더 걷기 좋다고 생각하십니까? 거리영상과 샴 네트워크 기반의 딥러닝 모델을 활용한 정성적 보행환경 평가.” 한국도시지리학회지, 27(1), 65-79.

10.21189/JKUGS.27.1.5
18

최재연･김소망･노승민･강영옥, 2024b, “거리영상과 딥러닝을 활용한 물리적 보행환경과 인지적 보행환경 평가,” 한국지도학회지, 24(3), 45-60.

10.16879/jkca.2024.24.3.045
19

최재연･노승민･김소망･강영옥, 2024c, “거리 영상과 시멘틱 세그먼테이션을 활용한 보행환경 평가,” 대한지리학회지, 59(5), 673-687.

20

허지은, 2010, CPTED 설계를 통한 환경디자인 개선에 관한 연구, 국민대학교 디자인대학원 석사학위논문.

21

Amiruzzaman, M., Curtis, A., Zhao, Y., Jamonnak, S. and Ye, X., 2021, Classifying crime places by neighborhood visual appearance and police geonarratives: A machine learning approach, Journal of Computational Social Science, 4(2), 813-837.

10.1007/s42001-021-00107-x33718652PMC7938887
22

Anderson, J. M., MacDonald, J. M., Bluthenthal, R. and Ashwood, J. S., 2013, Reducing crime by shaping the built environment with zoning: An empirical study of Los Angeles, University of Pennsylvania Law Review, 699-756.

10.2139/ssrn.2109511
23

Bijmolt, T. H. and Wedel, M., 1995, The effects of alternative methods of collecting similarity data for multidimensional scaling, International Journal of Research in Marketing, 12(4), 363-371.

10.1016/0167-8116(95)00012-7
24

Biljecki, F. and Ito, K., 2021, Street view imagery in urban analytics and GIS: A review, Landscape and Urban Planning, 215, 104217.

10.1016/j.landurbplan.2021.104217
25

Blečić, I., Cecchini, A. and Trunfio, G. A., 2018, Towards automatic assessment of perceived walkability, Computational Science and Its Applications–ICCSA 2018: 18th International Conference, July 2-5, Melbourne, 351-365.

10.1007/978-3-319-95168-3_24
26

Burges, C., Shaked, T., Renshaw, E., Lazier, A., Deeds, M., Hamilton, N. and Hullender, G., 2005, Learning to rank using gradient descent, In Proceedings of the 22nd International Conference on Machine Learning, August 7-11, Bonn, 89-96.

10.1145/1102351.1102363
27

Chen, X., Li, G., Mehmood, M. S., Jin, A., Du, M. and Xue, Y., 2023, Using street view images to examine the impact of built environment on street property crimes in the old district of CA City, China, Discrete Dynamics in Nature and Society, 2023(1), 1470452.

10.1155/2023/1470452
28

Cozens, P. and Love, T., 2015, A review and current status of crime prevention through environmental design (CPTED), Journal of Planning Literature, 30(4), 393-412.

10.1177/0885412215595440
29

Cozens, P. M., Saville, G. and Hillier, D., 2005, Crime prevention through environmental design (CPTED): A review and modern bibliography, Property Management, 23(5), 328-356.

10.1108/02637470510631483
30

Deng, M., Yang, W., Chen, C. and Liu, C., 2022, Exploring associations between streetscape factors and crime behaviors using Google Street View images, Frontiers of Computer Science, 16(4), 164316.

10.1007/s11704-020-0007-z
31

Doran, B. J. and Lees, B. G., 2005, Investigating the spatiotemporal links between disorder, crime, and the fear of crime, The Professional Geographer, 57(1), 1-12.

10.1111/j.0033-0124.2005.00454.x
32

Dubey, A., Naik, N., Parikh, D., Raskar, R. and Hidalgo, C. A., 2016, Deep learning the city: Quantifying urban perception at a global scale, Computer Vision–ECCV 2016: 14th European Conference, October 11-14, Amsterdam, Part I 14, 196-212.

10.1007/978-3-319-46448-0_12
33

Ferraro, K. F. and LaGrange, R. L., 1987, The measurement of fear of crime, Sociological Inquiry, 57(1), 70-97.

10.1111/j.1475-682X.1987.tb01181.x
34

Fisher, B. S. and Nasar, J. L., 1992, Fear of crime in relation to three exterior site features: Prospect, refuge, and escape, Environment and Behavior, 24(1), 35-65.

10.1177/0013916592241002
35

Guan, W., Chen, Z., Feng, F., Liu, W. and Nie, L., 2021, Urban perception: Sensing cities via a deep interactive multi- task learning framework, ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 17(1), 1-20.

10.1145/3424115
36

Ha, T., Oh, G. S. and Park, H. H., 2015, Comparative analysis of defensible space in CPTED housing and non- CPTED housing, International Journal of Law, Crime and Justice, 43(4), 496-511.

10.1016/j.ijlcj.2014.11.005
37

He, L., Páez, A. and Liu, D., 2017, Built environment and violent crime: An environmental audit approach using Google Street View, Computers, Environment and Urban Systems, 66, 83-95.

10.1016/j.compenvurbsys.2017.08.001
38

Hipp, J. R., Lee, S., Ki, D. and Kim, J. H., 2021, Measuring the built environment with Google Street View and machine learning: Consequences for crime on street segments, Journal of Quantitative Criminology, 38(3), 537-565.

10.1007/s10940-021-09506-9
39

Iqbal, A. and Ceccato, V., 2016, Is CPTED useful to guide the inventory of safety in parks? A study case in Stockholm, Sweden, International Criminal Justice Review, 26(2), 150-168.

10.1177/1057567716639353
40

Jackson, J., 2005, Validating new measures of the fear of crime, International Journal of Social Research Methodology, 8(4), 297-315.

10.1080/13645570500299165
41

Jeffery, C. R., 1971, Crime prevention through environmental design. American Behavioral Scientist, 14(4), 598-598.

10.1177/000276427101400409
42

Kang, Y., 2025, Human-centered geospatial data science, arXiv preprint, arXiv:2501.05595.

43

Kang, Y., Kim, J., Park, J. and Lee, J., 2023, Assessment of perceived and physical walkability using street view images and deep learning technology, ISPRS International Journal of Geo-Information, 12(5), 186.

10.3390/ijgi12050186
44

Kelling, G. L. and Wilson, J. Q., 1982, Broken windows, Atlantic Monthly, 249(3), 29-38.

45

Koch, G., Zemel, R. and Salakhutdinov, R., 2015, Siamese neural networks for one-shot image recognition, ICML Deep Learning Workshop, July 6-11, Lille, 2(1), 1-30.

46

Kohm, S. A., 2009, Spatial dimensions of fear in a high-crime community: Fear of crime or fear of disorder?, Canadian Journal of Criminology and Criminal Justice, 51(1), 1-30.

10.3138/cjccj.51.1.1
47

Lederer, D., 2012, Am I safe in my home? fear of crime analyzed with spatial statistics methods in a Central European city, Computational Science and Its Applications-ICCSA 2012: 12th International Conference, June 18-21, 2012, Salvador de Bahia, Part II 12, 263- 274.

10.1007/978-3-642-31075-1_20
48

Lee, I., Jung, S., Lee, J. and Macdonald, E., 2019, Street crime prediction model based on the physical characteristics of a streetscape: Analysis of streets in low-rise housing areas in South Korea, Environment and Planning B: Urban Analytics and City Science, 46(5), 862-879.

10.1177/2399808317735105
49

Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S. and Guo, B., 2021, Swin transformer: Hierarchical vision transformer using shifted windows, 2021 IEEE/ CVF International Conference on Computer Vision (ICCV), October 10-17, Montreal, 9992-10002.

10.1109/ICCV48922.2021.00986
50

Min, W., Mei, S., Liu, L., Wang, Y. and Jiang, S., 2019, Multi-task deep relative attribute learning for visual urban perception, IEEE Transactions on Image Processing, 29, 657-669.

10.1109/TIP.2019.2932502
51

Pain, R., 2000, Place, social relations and the fear of crime: A review, Progress in Human Geography, 24(3), 365-387.

10.1191/030913200701540474
52

Peeters, M. P. and Vander Beken, T., 2017, The relation of CPTED characteristics to the risk of residential burglary in and outside the city center of Ghent, Applied Geography, 86, 283-291.

10.1016/j.apgeog.2017.06.012
53

Rader, N., 2017, Fear of crime, Oxford Research Encyclopedia of Criminology and Criminal Justice.

10.1093/acrefore/9780190264079.013.10
54

Santani, D., Ruiz-Correa, S. and Gatica-Perez, D., 2018, Looking south: Learning urban perception in developing cities, ACM Transactions on Social Computing, 1(3), 1-23.

10.1145/3224182
55

Stewart, N., Brown, G. D. and Chater, N., 2005, Absolute identification by relative judgment, Psychological Review, 112(4), 881.

10.1037/0033-295X.112.4.881
56

Vrij, A. and Winkel, F. W., 1991, Characteristics of the built environment and fear of crime: A research note on interventions in unsafe locations, Deviant Behavior, 12(2), 203-215.

10.1080/01639625.1991.9967873
57

Wang, R., Yuan, Y., Liu, Y., Zhang, J., Liu, P., Lu, Y. and Yao, Y., 2019, Using street view data and machine learning to assess how perception of neighborhood safety influences urban residents’ mental health, Health and Place, 59, 102186.

10.1016/j.healthplace.2019.102186
58

Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J. M. and Luo, P., 2021, SegFormer: Simple and efficient design for semantic segmentation with transformers, Advances in Neural Information Processing Systems, 34, 12077-12090.

59

Xie, H., Liu, L. and Yue, H., 2022, Modeling the effect of streetscape environment on crime using street view images and interpretable machine-learning technique, International Journal of Environmental Research and Public Health, 19(21), 13833.

10.3390/ijerph19211383336360717PMC9655263
60

Xu, Y., Yang, Q., Cui, C., Shi, C., Song, G., Han, X. and Yin, Y., 2019, Visual urban perception with deep semantic- aware network, MultiMedia Modeling: 25th International Conference, MMM 2019, January 8-11, Thessaloniki, Part II 25, 28-40.

10.1007/978-3-030-05716-9_3
61

Yue, H., Liu, L., Xu, C., Song, G., Chen, J., He, L. and Duan, L., 2024, Investigating the diurnal effects of on-street population and streetscape physical environment on street theft crime: A machine learning and negative binomial regression approach using street view images, Applied Geography, 163, 103194.

10.1016/j.apgeog.2023.103194
62

Zeng, M., Mao, Y. and Wang, C., 2021, The relationship between street environment and street crime: A case study of Pudong New Area, Shanghai, China, Cities, 112, 103143.

10.1016/j.cities.2021.103143
63

Zhanjun, H. E., Wang, Z., Xie, Z., Wu, L. and Chen, Z., 2022, Multiscale analysis of the influence of street built environment on crime occurrence using street-view images, Computers, Environment and Urban Systems, 97, 101865.

10.1016/j.compenvurbsys.2022.101865
64

Zhou, H., Liu, L., Lan, M., Zhu, W., Song, G., Jing, F., Zhong, Y., Su, Z. and Gu, X., 2021, Using Google Street View imagery to capture micro built environment characteristics in drug places, compared with street robbery, Computers, Environment and Urban Systems, 88, 101631.

10.1016/j.compenvurbsys.2021.101631
Information
  • Publisher :The Korean Geographical Society
  • Publisher(Ko) :대한지리학회
  • Journal Title :Journal of the Korean Geographical Society
  • Journal Title(Ko) :대한지리학회지
  • Volume : 60
  • No :5
  • Pages :576-592
  • Received Date : 2025-07-11
  • Revised Date : 2025-08-25
  • Accepted Date : 2025-08-27
  • DOI :https://doi.org/10.22776/kgs.2025.60.5.576
Journal Informaiton Journal of the Korean Geographical Society Journal of the Korean Geographical Society
online submission
  • NRF
  • KISTI Current Status
  • KISTI Cited-by
  • KCI 문헌 유사도 검사
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close